Technological Infrastructures

The Annual Briefing of NAHV, the transnational initiative funded by the Clean Hydrogen Partnership through the Horizon Europe program, was held at the Urban Center of Trieste. The FVG Region is one of the institutional partners of the initiative together with the Croatian Ministry for Economy and Sustainable Development (MINGO) and the Slovenian Ministry for Environment and Energy. The second Annual Meeting of the NAHV Consortium hosted almost 100 delegates representing 37 project partners from Croatia, Slovenia and Italy. Jerneja Sedlar, NAHV Coordinator, Head of HSE’s Development and Investment Department, described the progress made in particular at the level of industrial test benches. Overall, 17 ‘Testbed’ industrial projects are being developed in different locations in all three partner countries, supported by a number of cross-cutting actions. In the final year of the NAHV Horizon Europe project, 2029, major industry players from all three countries aim to produce up to 5,000 tonnes of renewable hydrogen per year from renewable energy sources, intended for energy storage, distribution and use. It is expected that around 20% of the renewable hydrogen produced will be traded between participating countries, thus creating a primary regional market for hydrogen. The implementation of this ambitious initiative aims to facilitate the uptake of hydrogen-related solutions and enable actors in the emerging hydrogen ecosystem of the Northern Adriatic to independently produce, transmit, store and use renewable hydrogen, as well as promote further adoption in the future. The consortium prepared a comprehensive overview of 17 industrial pilots in the second edition of the NAHV Testbed Catalogue, which is available on the NAHV website.   Training of future professionals and experts   A number of education-related activities were aimed at promoting the training of future professionals and experts in the field of hydrogen technologies with the aim of ensuring interdisciplinary education covering science, technology, engineering and mathematics, as well as the financial and social aspects of hydrogen technologies. These activities are coordinated by the University of Rijeka with the participation of the Universities of Ljubljana and Trieste and the partners GITONE, ECUBES and META Circularity. The Consortium has started the preparation of vocational training programs with the support of the FVG Regional Administration and the Slovenian and Croatian ministries and other partners, to be financed through the European Social Fund. The development of micro-credentials for professionals in the reskilling and upskilling sector will be launched in the 2025-26 school year in collaboration between the universities involved.   The activities of the Stakeholder Advisory Forum (SAF)   Alberto Soraci from Area Science Park, who is the Coordinator of the Stakeholder Advisory Forum (SAF), briefly presented the purpose and functioning of this body, which aims to involve external partners in the initiative for consultation, implementation support and to seize the potential additional opportunities that emerge through the life of the project. “The preparatory activities conducted by Area Science Park for the launch of the NAHV AISBL, a non-profit association that will be established under Belgian law, have now advanced and are coming to an end,” said Stephen Taylor, strategic coordinator of the NAHV Joint Working Group, a governance body of the NAHV initiative. The objective of the NAHV AISBL is to ensure the long-term sustainability of the initiative’s results and their impact beyond the duration of the NAHV Horizon Europe project. This structure, which is open to NAHV partners and other interested stakeholders, can complement other initiatives as well. After the Northern Adriatic Clean Hydrogen Investment Platform (NACHIP), launched in autumn 2024, two other such initiatives have received funding from the EU, H2Ready and NASCHA. All these projects received support from the NAHV Joint Working Group in the application phase and plan to integrate with the NAHV SPV at the end of their lifecycle. H2Ready is a bilateral Interreg Italy-Slovenia initiative to which 700 thousand euros of funding have been allocated to address the key challenge of the energy transition by involving municipalities in the development and implementation of hydrogen solutions. The project aims to strengthen the involvement of municipalities in the energy transition, leveraging their key potential as intermediaries between energy needs, infrastructure development and social innovation. In a consortium H2READY of 6 partners led by GOLEA, a regional development agency based in Nova Gorica, it integrates the public sector as a key player in ensuring a critical mass demand for hydrogen. The North Adriatic Smart Communities Hydrogen Accelerator (NASCHA), led by Area Science Park , aims to accelerate transnational innovation in the Northern Adriatic hydrogen ecosystem, validating and demonstrating renewable hydrogen technologies in Croatia, Slovenia and Friuli-Venezia Giulia through pilot solutions, improving investor readiness through three Smart Communities of Practice, two pilot projects across hydrogen storage and retail, scalable across communities. NASCHA is based on the North Adriatic Hydrogen Valley (NAHV) and NACHIP initiatives, aimed at the value chains of transport and mobility, urban and agricultural areas. Similar to NACHIP, NASCHA received €7.9 million in funding from the Interregional Innovation Investments (I3) facility under the European Regional Development Fund (ERDF), managed by the European Innovation Council and SMEs Executive Agency (EISMEA). Photo credit: Mariia Bortiakova

Area Science Park has launched a call for applications for the awarding of six scholarships aimed at university students working on their master’s degree thesis within the scope of the project “Support for the Diagnosis of Rare Diseases through Artificial Intelligence”. The project aims to develop innovative tools for early identification of rare diseases through the automated analysis of clinical data. The scholarships, which last six months and are renewable for an additional semester, will support the training of university students during the completion of their master’s degree thesis in one of the following subject areas: Multimodal modelling with AI, to distinguish normal conditions from pathological ones through advanced algorithms. Management and anonymisation of clinical databases (Electronic Health Records – EHR), with focus on interoperability and data security. Development of a digital ecosystem for clinical data research, integrated with the ORFEO data center. The selected candidates will carry out their research activities at the Area Science Park Data Engineering Laboratory (LADE) and will be able to access an advanced technological ecosystem, including the Orfeo computing platform. To apply, students must be enrolled in a master’s degree programme in related fields and must submit their application via certified email (PEC) by 11.59 pm on 16 March 2025. Selection will be based on the evaluation of qualifications and an interview. Further details and the full call for applications are available here.

The Data Engineering Laboratory (LADE) at Area Science Park has recently published an article in Nature – Scientific Data on protein sequence annotation. Thanks to technological advances in genomic sequencing, the number of known protein sequences has grown exponentially. Many of these sequences come from metagenomic projects that analyze environmental and clinical samples. Among the most relevant datasets in this field stands the Unified Human Gastrointestinal Proteome (UHGP) catalog, with a variety of applications in medicine and biology. However, the limited annotation of these sequences reduces their effectiveness. To address this issue, the DPCfam-UHGP dataset was developed, classifying UHGP sequences into protein families that typically group proteins sharing the same biological function. The dataset contains 10,778 families, generated through DPCfam clustering, an unsupervised method that organizes sequences into single- or multi-domain architectures. This project, part of Federico Barone‘s doctoral research supervised by Alessio Ansuini and Alberto Cazzaniga, exemplifies the fruitful interaction between data management and data science. In this context, the construction of a curated database of gastrointestinal proteins enabled more refined cataloging through advanced machine learning algorithms, allowing continuous database updates in fruitful feedback loop aimed at promoting new discoveries. The DPCfam-UHGP50 dataset, accessible through a web server, was developed following the best FAIR (Findable, Accessible, Interoperable, Reusable) practices, with the aim of fostering new discoveries in the field of human gastrointestinal tract metagenomics. Previously, LADE had already produced the DPCfam-UR50 database, accompanied by a publication in PLOS – Computational Biology.

The Data Engineering Laboratory (LADE) at Area Science Park has recently published an innovative study into Bioinformatics, opening up new perspectives in the study of proteins, the fundamental building blocks of life. In fact, Francesca Cuturello, Marco Celoria, Alessio Ansuini and Alberto Cazzaniga, the authors of the study, have demonstrated how artificial intelligence can predict the impact of genetic mutations on protein stability, helping to get a better understanding of the mechanisms underlying many diseases and potentially developing new treatments. The genome of living beings is constantly mutating due to external agents or random events and this leads us to observe changes in the sequences of the proteins they synthesise. Conducted as part of the Pathogen Readiness Platform for CERIC-ERIC (PRP@CERIC) project, the study uses AI models similar to GPT, applied to proteomics. These models are based on the analogy between a protein sequence and a sentence, with amino acids acting as “words”, allowing algorithms trained on hundreds of millions of protein sequences to be applied. Using this technique, the LADE researchers were able to predict how small variations in the amino acid sequence, such as those induced by mutations, can affect protein stability. A particularly innovative aspect is the use of the MSA Transformer model, which utilises information on the ancestral relationships between protein sequences to enhance the accuracy of predictions. The algorithm developed by LADE offers cutting-edge performance and will be made available to the scientific community to encourage further advancements in this field. “Predicting the effect of protein mutations through artificial intelligence allows us to explore, with great precision, complex biological phenomena that, until recently, were difficult to observe directly”, explains Francesca Cuturello, the study’s lead author. “This technology is a step forward towards innovative therapeutic solutions for a wide range of diseases.” The team’s work has already received widespread recognition, including Francesca Cuturello’s invitation to the prestigious Research Retreat “Physics of Biological Data Analysis” at the Aspen Center for Physics and it will be presented at other international research centres, such as the ICTP and the Leibniz Center for Informatics. For more information about LADE’s activities, click here.

Francesco Ortu was awarded the Artificial Intelligence Prize from the University of Trieste for his thesis “Interpreting How Large Language Models Handle Facts and Counterfactuals through Mechanistic Interpretability” as part of the Master’s program in “Data Science and Scientific Computing”. This work was developed at the Institute for Research and Technological Innovation (RIT) of Area Science Park. The study focuses on how generative language models, like those behind ChatGPT, react when presented with text containing false information. The work was published in the Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics and presented last August in Bangkok at one of the most important conferences on Computational Linguistics and Artificial Intelligence for Natural Language. “Research on interpretability,” explains Francesco Ortu, “aims to bridge the gap between empirical approaches and our scientific understanding of the inner workings of generative language models (LLMs). So far, most existing research in this area has focused on how models copy or recall factual knowledge. In our study, we analyzed how information propagates within the neural network, identifying the ‘neurons’ that choose whether to promote or suppress false information proposed by the user.” Congratulations to Francesco, with best wishes for pursuing exciting discoveries during his PhD, which will soon begin at the Laboratory of Data Engineering in Area Science Park.